LangPert：面向鲁棒物体重排的任务级扰动检测与处理
LangPert: Detecting and Handling Task-level Perturbations for Robust Object Rearrangement
AI总结：
针对物体重排任务中任务级扰动（TLP）的挑战，提出基于语言的框架LangPert，集成视觉语言模型监控扰动、利用分层思维链增强大语言模型推理，有效提升任务完成率与执行效率。
摘要：
物体重排的任务执行可能受到任务级扰动（TLP）的挑战，即意外的物体添加、移除和位移，这些会干扰底层视觉策略，从根本上影响任务可行性和进度。为应对这些挑战，我们提出LangPert，一个基于语言的框架，用于检测和缓解桌面重排任务中的TLP情况。LangPert集成视觉语言模型（VLM）以全面监控策略的技能执行和环境TLP，同时利用分层思维链（HCoT）推理机制增强大语言模型（LLM）的语境理解，生成自适应的纠正性技能执行计划。实验结果表明，LangPert比基线方法更有效处理多样TLP情况，实现更高任务完成率、提升执行效率，并可能泛化到未见过的场景。
英文摘要：
Task execution for object rearrangement could be challenged by Task-Level Perturbations (TLP), i.e., unexpected object additions, removals, and displacements that can disrupt underlying visual policies and fundamentally compromise task feasibility and progress. To address these challenges, we present LangPert, a language-based framework designed to detect and mitigate TLP situations in tabletop rearrangement tasks. LangPert integrates a Visual Language Model (VLM) to comprehensively monitor policy's skill execution and environmental TLP, while leveraging the Hierarchical Chain-of-Thought (HCoT) reasoning mechanism to enhance the Large Language Model (LLM)'s contextual understanding and generate adaptive, corrective skill-execution plans. Our experimental results demonstrate that LangPert handles diverse TLP situations more effectively than baseline methods, achieving higher task completion rates, improved execution efficiency, and potential generalization to unseen scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
